{"id":"W4384665361","doi":"10.1007/s00521-023-08696-6","title":"Comparing explanations in RL","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Downstream (manufacturing); Context (archaeology); Artificial intelligence; Reinforcement; Test (biology); Machine learning; Human–computer interaction; Data science; Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005189091,0.0008033894,0.0009526731,0.001812752,0.0006086375,0.002781328,0.001511755,0.002206105,0.01742319],"category_scores_gemma":[0.04876632,0.000438414,0.001124757,0.0009830372,0.001714247,0.006121711,0.002194639,0.002271383,0.001121058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001603775,"about_ca_system_score_gemma":0.0009334374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002305862,"about_ca_topic_score_gemma":0.002375341,"domain_scores_codex":[0.9946249,0.003337938,0.0002947619,0.0007704938,0.0007240808,0.0002477254],"domain_scores_gemma":[0.9631914,0.03238004,0.0007939484,0.002326052,0.0008730176,0.0004355939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002074175,0.0003184607,0.01366773,0.0005841493,0.0005974303,0.0004979771,0.001105763,0.3009921,0.002233154,0.3186004,0.009633705,0.3496949],"study_design_scores_gemma":[0.0001589384,0.0001996537,0.002606062,0.00007919115,0.0001159646,0.00009788459,0.0002907508,0.5449715,0.001598014,0.4460097,0.003830738,0.0000415195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3665618,0.004346836,0.5585032,0.006160296,0.0006591198,0.000221562,0.001296217,0.00327918,0.05897166],"genre_scores_gemma":[0.9518088,0.0003245788,0.04229266,0.0002861995,0.00008748934,0.00006174794,0.0008111905,0.0002138859,0.004113447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01742319,"threshold_uncertainty_score":0.05828637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0647685377314945,"score_gpt":0.3219865554596638,"score_spread":0.2572180177281693,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}